{"ID":6537742,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11215","arxiv_id":"2607.11215","title":"Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation","abstract":"Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existing multilingual SLT approaches still struggle to learn a unified model that minimizes cross-lingual conflicts while capturing shared cross-lingual semantics and preserving language-specific variations across different sign languages. Therefore, we propose Q-BridgeNet, a unified framework for multilingual SLT that jointly mitigates cross-lingual conflicts across both the sign language and spoken language sides. On the sign language side, Q-BridgeNet learns discrete Q-units via adaptive segmentation and residual vector quantization: a shared base codebook provides language-agnostic semantic primitives, while language-specific residual codebooks refine heterogeneous signing semantics. On the spoken language side, a multilingual LLM is fine-tuned to operate in the Q-unit space, leveraging cross-lingual priors to enable a unified SLT model. Experiments on PHOENIX14T, How2Sign, and CSL-Daily show that Q-BridgeNet effectively mitigates cross-lingual conflicts, achieving state-of-the-art performance on native sign-spoken pairs while also demonstrating strong generalization to non-native pairs. Our source code is publicly available at: https://github.com/FengLiQ/Q-BridgeNet","short_abstract":"Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existin...","url_abs":"https://arxiv.org/abs/2607.11215","url_pdf":"https://arxiv.org/pdf/2607.11215v1","authors":"[\"Liqian Feng\",\"Lintao Wang\",\"Xiaochen Liu\",\"Anusha Withana\",\"Ken-Tye Yong\",\"Dehui Kong\",\"Zhiyong Wang\",\"Kun Hu\"]","published":"2026-07-13T08:09:03Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.MM\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":614227,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6537742,"paper_url":"https://arxiv.org/abs/2607.11215","paper_title":"Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation","repo_url":"https://github.com/FengLiQ/Q-BridgeNet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}